AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation

arXiv:2610.07457 · cs.LG, cs.AI, cs.CL · Submitted 2026-10-05 · Read on arXiv

cs.LG, cs.AI, cs.CL

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/HanzhiZhang-Ulrica/AlignQuant

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Quantization — 1× in this paper · explained in 12 episodes

Sources

• Channel-Wise Mixed-Precision Quantization for Large Language Models
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
• MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference
• Measuring Massive Multitask Language Understanding
• FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference
• OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
• SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
• BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference
• ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs
• Pointer Sentinel Mixture Models
• SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models
• ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
• FlatQuant: Flatness Matters for LLM Quantization
• LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks